{"id":"https://openalex.org/W4414920927","doi":"https://doi.org/10.1109/iccv51701.2025.00251","title":"Stable-Sim2Real: Exploring Simulation of Real-Captured 3D Data with Two-Stage Depth Diffusion","display_name":"Stable-Sim2Real: Exploring Simulation of Real-Captured 3D Data with Two-Stage Depth Diffusion","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414920927","doi":"https://doi.org/10.1109/iccv51701.2025.00251"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.23483","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066673615","display_name":"Mutian Xu","orcid":"https://orcid.org/0000-0001-8123-6493"},"institutions":[{"id":"https://openalex.org/I4210105385","display_name":"Shanghai Stock Exchange","ror":"https://ror.org/01ecwsw76","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210105385"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mutian Xu","raw_affiliation_strings":["SSE, CUHKSZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SSE, CUHKSZ","institution_ids":["https://openalex.org/I4210105385","https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113156008","display_name":"Chongjie Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chongjie Ye","raw_affiliation_strings":["FNii-Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FNii-Shenzhen","institution_ids":["https://openalex.org/I3131625388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100674214","display_name":"Haolin Liu","orcid":"https://orcid.org/0009-0002-5583-2974"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haolin Liu","raw_affiliation_strings":["Tencent Hunyuan3D"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Hunyuan3D","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034378184","display_name":"Yushuang Wu","orcid":"https://orcid.org/0009-0002-9725-0606"},"institutions":[{"id":"https://openalex.org/I4210147622","display_name":"Groupe d'Analyse et de Th\u00e9orie Economique Lyon St Etienne","ror":"https://ror.org/042fmc481","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I188626449","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I4210147622","https://openalex.org/I4405259976","https://openalex.org/I51195161"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yushuang Wu","raw_affiliation_strings":["ByteDance Games"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Games","institution_ids":["https://openalex.org/I4210147622"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052192323","display_name":"Jiahao Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105385","display_name":"Shanghai Stock Exchange","ror":"https://ror.org/01ecwsw76","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210105385"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Chang","raw_affiliation_strings":["SSE, CUHKSZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SSE, CUHKSZ","institution_ids":["https://openalex.org/I4210105385","https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081098250","display_name":"Xiaoguang Han","orcid":"https://orcid.org/0000-0003-0810-259X"},"institutions":[{"id":"https://openalex.org/I4210105385","display_name":"Shanghai Stock Exchange","ror":"https://ror.org/01ecwsw76","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210105385"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoguang Han","raw_affiliation_strings":["SSE, CUHKSZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SSE, CUHKSZ","institution_ids":["https://openalex.org/I4210105385","https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5066673615"],"corresponding_institution_ids":["https://openalex.org/I4210105385","https://openalex.org/I4210116924"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.46660983,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2609","last_page":"2619"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9729999899864197,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9729999899864197,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9179999828338623,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5852000117301941},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5609999895095825},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.5503000020980835},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4652000069618225},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4496000111103058},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4221000075340271},{"id":"https://openalex.org/keywords/3d-simulation","display_name":"3d simulation","score":0.38510000705718994},{"id":"https://openalex.org/keywords/computer-simulation","display_name":"Computer simulation","score":0.35929998755455017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.640500009059906},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5852000117301941},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5609999895095825},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5503000020980835},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4652000069618225},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44780001044273376},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4221000075340271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4172999858856201},{"id":"https://openalex.org/C2983771295","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"3d simulation","level":2,"score":0.38510000705718994},{"id":"https://openalex.org/C500300565","wikidata":"https://www.wikidata.org/wiki/Q925667","display_name":"Computer simulation","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3285999894142151},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28790000081062317},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C84824328","wikidata":"https://www.wikidata.org/wiki/Q4633097","display_name":"2D to 3D conversion","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2565999925136566},{"id":"https://openalex.org/C2777897806","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3D modeling","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.23483","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.23483","pdf_url":"https://arxiv.org/pdf/2507.23483","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.23483","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.23483","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.23483","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.23483","pdf_url":"https://arxiv.org/pdf/2507.23483","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2719502696","display_name":null,"funder_award_id":"62172348","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"3D":[0,12,21,25,80,152,162,175,187,199],"data":[1,26,55,163,177,201],"simulation":[2,27,164],"aims":[3],"to":[4,35,53,97,144,160],"bridge":[5],"the":[6,37,99,102,127,171,174,191,194],"gap":[7],"between":[8,101,197],"simulated":[9,176,200],"and":[10,104,129,202],"real-captured":[11,203],"data,":[13],"which":[14],"is":[15,142],"a":[16,57,74,86,109,136,151,156],"fundamental":[17],"problem":[18],"for":[19],"real-world":[20,186],"visual":[22,188],"tasks.":[23,189],"Most":[24],"methods":[28],"inject":[29],"predefined":[30],"physical":[31],"priors":[32],"but":[33,60,111],"struggle":[34],"capture":[36],"full":[38],"complexity":[39],"of":[40,78],"real":[41,103],"data.":[42],"An":[43],"optimal":[44],"approach":[45],"involves":[46],"learning":[47],"an":[48],"implicit":[49],"mapping":[50],"from":[51,120,179],"synthetic":[52,105,128],"realistic":[54,121],"in":[56,62,68,185],"data-driven":[58,79],"manner,":[59],"progress":[61],"this":[63],"solution":[64,76],"has":[65],"met":[66],"stagnation":[67],"recent":[69],"studies.":[70],"This":[71],"work":[72],"explores":[73],"new":[75,157],"path":[77],"simulation,":[81],"called":[82],"Stable-Sim2Real,":[83],"based":[84],"on":[85],"novel":[87],"two-stage":[88],"depth":[89,132],"diffusion":[90,140],"model.":[91],"The":[92],"initial":[93,130],"stage":[94],"finetunes":[95],"Stable-Diffusion":[96],"generate":[98],"residual":[100],"paired":[106],"depth,":[107,113],"producing":[108],"stable":[110],"coarse":[112],"where":[114,139],"some":[115],"local":[116],"regions":[117],"may":[118],"deviate":[119],"patterns.":[122,204],"To":[123],"enhance":[124],"this,":[125],"both":[126],"output":[131],"are":[133],"fed":[134],"into":[135],"second-stage":[137],"diffusion,":[138],"loss":[141],"adjusted":[143],"prioritize":[145],"these":[146],"distinct":[147],"areas":[148],"identified":[149],"by":[150],"discriminator.":[153],"We":[154],"provide":[155],"benchmark":[158],"scheme":[159],"evaluate":[161],"methods.":[165],"Extensive":[166],"experiments":[167],"show":[168],"that":[169],"training":[170],"network":[172],"with":[173],"derived":[178],"our":[180,198],"method":[181],"significantly":[182],"enhances":[183],"performance":[184],"Moreover,":[190],"evaluation":[192],"demonstrates":[193],"high":[195],"similarity":[196],"Project":[205],"page:":[206],"https://mutianxu.github.io/stable-sim2real/.":[207]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}